A detailed study from technical infrastructure expert Bryan Berg reveals that Comcast may be prioritizing traffic for its own Xfinity app for Xbox 360 over other services, like Netflix — which, if accurate, would be a bold deviation from the spirit of the FCC's net neutrality principles. This isn't the first time an issue has arisen with Comcast's Xfinity app, as the company's decision to exempt its app from bandwidth caps raised the eyebrows of net neutrality advocates, including Senator Al Franken (D-MN). But this latest accusation is much more serious than the bandwidth cap issue, since bandwidth prioritization could have a material impact on the quality of service of Comcast's competitors in comparison to the company's own offering.
"Contrary to what has been widely speculated, the Xfinity traffic uses the same downstream channels as regular internet traffic."
Comcast has argued that its Xfinity service is exempt from the FCC's net neutrality principles because it is delivered over its own private network rather than the open internet. But Berg says that "contrary to what has been widely speculated, the Xfinity traffic is not delivered via separate, dedicated downstream channel(s) — it uses the same downstream channels as regular internet traffic." Additionally, Berg notes that "Comcast openly admits to prioritizing certain kinds of traffic — like their digital voice product" and that "it's clear that some configuration is in place to do so." He concludes that "Comcast is using separate DOCSIS service flows to prioritize the traffic to the Xfinity Xbox app," and that "this separation allows them to exempt that traffic from both bandwidth cap accounting and download speed limits."
To test the network, Berg devised a script that monitored the downstream channels providing bandwidth to his modem, and found that Xfinity traffic uses the same RF spectrum as public internet traffic. Berg argues that if Comcast was using dedicated (i.e. private) channels to deliver Xfinity traffic, only those channels would increase when streaming video in the app — but he says "instead, like any other internet traffic, the Xfinity traffic is directly observable to be balanced (approximately) evenly across all 4 of the downstream channels." Additionally, Berg created a script that started 24 simultaneous downloads of Google Chrome to simulate local network congestion, in order to test potential rate limiting. He found that when terminating the script, "the bandwidth available to the Netflix app increases," and that "when the Netflix app is not experiencing this congestion the video quality shows a corresponding improvement." In contrast, Berg says that "if I run the Xfinity app, the video quality is seemingly unaffected by the synthetic traffic," and "unlike the Netflix example, the amount of bandwidth available to internet traffic is unaffected."
"Berg's work is incredibly important... his findings should be evaluated by the FCC."
Berg's local analysis is certainly not a definitive look at Comcast's overall network, but it's an interesting data point in light of growing concern over the ISP's network operations. Art Brodsky from Public Knowledge tells us that "Berg's work is incredibly important," and that "his findings should be evaluated by the FCC or other agencies to see if there are more violations." We have asked Comcast to comment on the matter and will update you with any additional information as it becomes available.